© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 7-GEMMASCOPE-TRANSCODER-16K
    7. 13130
    Prev
    Next
    INDEX
    Explanations

    scientific journals and publications.

    oai_token-act-pair · gemini-2.0-flash

    academic publications

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     myſelf
    -0.99
     itſelf
    -0.81
     Eſ
    -0.77
     Efq
    -0.74
     himſelf
    -0.73
     whoſe
    -0.73
     Monfieur
    -0.72
     becauſe
    -0.69
     poffible
    -0.69
     themſelves
    -0.66
    POSITIVE LOGITS
    <bos>
    0.56
    :+:
    0.45
     des
    0.44
    ?
    0.44
    ForEach
    0.44
     j
    0.43
     chande
    0.43
    adaptiveStyles
    0.41
    bou
    0.40
     gar
    0.40
    Activations Density 1.383%

    No Known Activations